def get_kaggle_reader(validation_pct=.2):
train_file = Path('./train.zip')
test_file = Path('./test.zip')
if not train_file.is_file() or not test_file.is_file():
print('👇👇👇👇👇👇👇👇👇👇👇👇👇')
print(
'Please put train.zip and test.zip from '
'https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition to project root path.'
)
raise FileNotFoundError()
train_arc = ZipTarReader.auto(train_file.name)
test_arc = ZipTarReader.auto(test_file.name)
file_list = train_arc.shuffled_namelist()
file_list = np.array(file_list)
mid = int(len(file_list) * validation_pct)
train_file_list = file_list[mid:]
vali_file_list = file_list[:mid]
return BatchReader.BatchReader(train_arc, train_file_list, KaggleLabelClassifier),\
BatchReader.BatchReader(train_arc, vali_file_list, KaggleLabelClassifier),\
BatchReader.BatchReader(test_arc, test_arc.namelist(), KaggleLabelClassifier)
def get_reader(filename):
arc = ZipTarReader.auto(filename)
return BatchReader.BatchReader(arc, arc.namelist(), KaggleLabelClassifier)
import BatchReader as dataset
import tensorflow as tf
import numpy as np
max_it =int(1e4 + 1)
IMAGE_HEIGHT = 64
IMAGE_WIDTH = 256
MAX_CAPTCHA = 5
CHAR_SET_LEN = 10
batch_size = 64
file = open('acc.txt','a')
train_dataset_reader = dataset.BatchReader(index_file='index')
X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT*IMAGE_WIDTH])
Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA*CHAR_SET_LEN])
keep_prob = tf.placeholder(tf.float32) # dropout
# CNN
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):
x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
# 4 conv layer
w_c1 = tf.Variable(w_alpha*tf.random_normal([3, 3, 1, 32]))
b_c1 = tf.Variable(b_alpha*tf.random_normal([32]))
conv1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w_c1, strides=[1, 1, 1, 1], padding='SAME'), b_c1))
conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
conv1 = tf.nn.dropout(conv1, keep_prob)
w_c2 = tf.Variable(w_alpha*tf.random_normal([3, 3, 32, 64]))
b_c2 = tf.Variable(b_alpha*tf.random_normal([64]))
conv2 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv1, w_c2, strides=[1, 1, 1, 1], padding='SAME'), b_c2))
import BatchReader as dataset
import os
import time
from CaptchaModel import Captcha
# load model
model = Captcha()
model.load_checkpoint('crack_capcha0.994400002956.model-9960')
# load dataset
dataset = dataset.BatchReader(ratio=0.01, test_size=1000)
images, labels = dataset.get_val_batch(0, 1000)
count = len(labels)
correct = 0
# start timing
start = time.time()
t = start
# start testing
for i in range(count):
image = images[i]
label = labels[i]
pred = model.predict(image)
text = ''.join(map(str, pred))
if text == label:
correct += 1
else:
print(label, text)
pass
